SlideShare a Scribd company logo
1 of 28
See the Earth as it could be.
Eric Culbertson
Data Scientist, Astraea
• 3D buildings models have many different use cases
• Solar potential estimation
• Utility management
• Disaster planning and simulation
2
How are 3D Models Made?
• Standard approaches:
• Use LiDAR point clouds to create 3D mesh
• Stitch imagery taken at multiple angles to the mesh
3
• Constructing these 3D models can be labor intensive and
expensive (both in compute power $$$)
• Is there an alternative using
• Free data?
• Open Source tools?
4
• Quality of 3D model is
quantified by the level of detail
(LOD) metric
• Higher LOD = more versatile
• But also more difficult to obtain
5
What do I Mean by 3D?
• Quality of 3D model is
quantified by the level of detail
(LOD) metric
• Higher LOD = more versatile
• But also more difficult to obtain
6
What do I Mean by 3D?
Machine Learning
• Machine learning can be applied to solve difficult problems
without the need of a subject matter expert
• Recent advances in deep learning on images have made great
strides
• Machine learning tools are open source
7
• Eventually predict labels for new data
( , ? ?)
8
( , )
• Start by feeding many examples with the correct predictions
Input imagery building
footprints
building
height
Application to Overhead Imagery
Imagery Sources
• Overhead imagery is available from many different sources in
my region of interest (Las Vegas)
9
Name Source Bands Resolution (m) Coverage Revisit Cost
Worldview 3 Satellite 8 0.3 m ~ Globe ~ daily $$$$$$
NAIP Aerial 4 1.0 m U.S. 3 years Free
Sanborn Aerial 4 0.3 m Partial U.S. 3 years Free - $
Imagery Sources
• Overhead imagery is available from many different sources in my
region of interest (Las Vegas)
• Most time was spent with 2015 NAIP and 2016 Sanborn imagery
10
Name Source Bands Resolution (m) Coverage Revisit Cost
Worldview 3 Satellite 8 0.3 m ~ Globe ~ daily $$$$$$
NAIP Aerial 4 1.0 m U.S. 3 years Free
Sanborn Aerial 4 0.3 m Partial U.S. 3 years Free - $
Imagery Sources
11
NAIP imagery Sanborn imagery
Ground Truth
• Building footprint polygons were provided by the SpaceNet Challenge
• Rasterized with rasterio, shapely, and numpy python modules
• Pixel height truth was derived from 2012 LiDAR data found on USGS
• Quality level is not ideal (pulse density ~ .3 pulses / m2)
12
Raw Lidar point cloud tiles
Filter outliers
Merge tiles
Height above ground
Reproject
Rasterize
Pixel heights
Las2las
PDAL
CloudCompare
Neuron / Perceptron
13
11
11
8
2
𝑤𝑖 ∗ 𝑥𝑖
Weighted sum
Cat
Prediction
Body length
Tail length
Weight
Number of ears
Activation
Dog
Neural Network
14
10
11
8
2
Sum + activation
Cat
Prediction
Body length
Tail length
Weight
Number of ears
1.0
8
Body length
Tail length
Weight
• Nesting layers of neurons allows the network to learn more
complicated features
Dog
Convolutional Neural Network
• CNNs are a way to extract important features from an image to
make a prediction
15LearnedFeatures
Sum + activation
Prediction
Cat
Dog
CNN Image Segmentation
16
• CNNs also can be used to make predictions per-pixel by
determining important features in regions around that pixel
U-net architecture
Application to Overhead Imagery
17
Predict footprints
Predict pixel height
• Similar features are used to determine the building footprint and height
• Combining the learning process shares knowledge gained from learning
each task
• This saves time and manual effort
Input imagery
Shared weights
Combine To make
2.5D model
• Keras was used to implement the U-net architecture
• High level wrapper of either Tensorflow, Theano or CNTK
• Allows for fast experimentation
• Simple to use, but flexible
18
FOSS for Deep Learning
• NAIP shows some promise in getting building height
• Roof shape seems beyond its capability
19
NAIP imagery LiDAR Height Predicted Height
Challenges
20
NAIP imagery Lidar Height
This is a ditch, not a
raised area
Challenges
21
• NAIP and Sanborn imagery do
not line up well with ground
truth polygons
• Offset is not consistent
NAIP Results
• Accuracy of only 35%
• Performs well on short
structures
• Biased to predict 2 story
buildings
22
Predicted Num Stories
TrueNumStories
Sanborn Results
• Accuracy improves to 56%
• Still struggles on
residential sized buildings
23
Predicted Num Stories
TrueNumStories
24
True Heights
25
NAIP Results
26
Sanborn Results
Conclusions
• Promising
• On the horizon
• Needs better height data
• Needs high res imagery
27
Acknowledgements
• SpaceNet Challenge
• Accurate ground truth footprints were quite valuable
• Kohei Ozaki
• His solution to the SpaceNet challenge introduced me to image segmentation
28

More Related Content

What's hot

Surveying the Trends in Geospatial Data: From Pixels to Point Clouds
Surveying the Trends in Geospatial Data: From Pixels to Point CloudsSurveying the Trends in Geospatial Data: From Pixels to Point Clouds
Surveying the Trends in Geospatial Data: From Pixels to Point CloudsSafe Software
 
Integrating eo with official statistics using machine learning in mexico geo ...
Integrating eo with official statistics using machine learning in mexico geo ...Integrating eo with official statistics using machine learning in mexico geo ...
Integrating eo with official statistics using machine learning in mexico geo ...Abel Alejandro Coronado Iruegas
 
2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...
2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...
2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...GIS in the Rockies
 
Processing Geospatial Data At Scale @locationtech
Processing Geospatial Data At Scale @locationtechProcessing Geospatial Data At Scale @locationtech
Processing Geospatial Data At Scale @locationtechRob Emanuele
 
Enabling Access to Big Geospatial Data with LocationTech and Apache projects
Enabling Access to Big Geospatial Data with LocationTech and Apache projectsEnabling Access to Big Geospatial Data with LocationTech and Apache projects
Enabling Access to Big Geospatial Data with LocationTech and Apache projectsRob Emanuele
 
Using Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in MiningUsing Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in MiningArgongra Gis
 
Pleiades - satellite imagery - very high resolution
Pleiades - satellite imagery - very high resolutionPleiades - satellite imagery - very high resolution
Pleiades - satellite imagery - very high resolutionSpot Image
 
Session 08 geospatial data
Session 08 geospatial dataSession 08 geospatial data
Session 08 geospatial databodaceacat
 
Using Pleiades Very High Resolution Images for planning activities in feasib...
Using Pleiades  Very High Resolution Images for planning activities in feasib...Using Pleiades  Very High Resolution Images for planning activities in feasib...
Using Pleiades Very High Resolution Images for planning activities in feasib...Argongra Gis
 
Remote Sensing Data — Instant Home Delivery!
Remote Sensing Data — Instant Home Delivery!Remote Sensing Data — Instant Home Delivery!
Remote Sensing Data — Instant Home Delivery!Safe Software
 
Processing Geospatial at Scale at LocationTech
Processing Geospatial at Scale at LocationTechProcessing Geospatial at Scale at LocationTech
Processing Geospatial at Scale at LocationTechRob Emanuele
 
Remote sensing analysis
Remote sensing analysisRemote sensing analysis
Remote sensing analysisFAO
 
Ahmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili BiliAhmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili BiliHartanto Sanjaya
 
Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...
Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...
Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...Christian Kehl
 
Processing Rasters from Satellites, Drones, & More
Processing Rasters from Satellites, Drones, & MoreProcessing Rasters from Satellites, Drones, & More
Processing Rasters from Satellites, Drones, & MoreSafe Software
 

What's hot (20)

Surveying the Trends in Geospatial Data: From Pixels to Point Clouds
Surveying the Trends in Geospatial Data: From Pixels to Point CloudsSurveying the Trends in Geospatial Data: From Pixels to Point Clouds
Surveying the Trends in Geospatial Data: From Pixels to Point Clouds
 
Integrating eo with official statistics using machine learning in mexico geo ...
Integrating eo with official statistics using machine learning in mexico geo ...Integrating eo with official statistics using machine learning in mexico geo ...
Integrating eo with official statistics using machine learning in mexico geo ...
 
Machine learning and Satellite Images
Machine learning and Satellite ImagesMachine learning and Satellite Images
Machine learning and Satellite Images
 
2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...
2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...
2018 GIS in the Rockies Vendor Showcase (Th): ERDAS Imagine What's New and Ti...
 
What's new in ar kit 2
What's new in ar kit 2What's new in ar kit 2
What's new in ar kit 2
 
Processing Geospatial Data At Scale @locationtech
Processing Geospatial Data At Scale @locationtechProcessing Geospatial Data At Scale @locationtech
Processing Geospatial Data At Scale @locationtech
 
Enabling Access to Big Geospatial Data with LocationTech and Apache projects
Enabling Access to Big Geospatial Data with LocationTech and Apache projectsEnabling Access to Big Geospatial Data with LocationTech and Apache projects
Enabling Access to Big Geospatial Data with LocationTech and Apache projects
 
Projections
ProjectionsProjections
Projections
 
Using Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in MiningUsing Very High Resolution Satellite Images for Planning Activities in Mining
Using Very High Resolution Satellite Images for Planning Activities in Mining
 
Mapreduce
MapreduceMapreduce
Mapreduce
 
Pleiades - satellite imagery - very high resolution
Pleiades - satellite imagery - very high resolutionPleiades - satellite imagery - very high resolution
Pleiades - satellite imagery - very high resolution
 
Session 08 geospatial data
Session 08 geospatial dataSession 08 geospatial data
Session 08 geospatial data
 
Using Pleiades Very High Resolution Images for planning activities in feasib...
Using Pleiades  Very High Resolution Images for planning activities in feasib...Using Pleiades  Very High Resolution Images for planning activities in feasib...
Using Pleiades Very High Resolution Images for planning activities in feasib...
 
Remote Sensing Data — Instant Home Delivery!
Remote Sensing Data — Instant Home Delivery!Remote Sensing Data — Instant Home Delivery!
Remote Sensing Data — Instant Home Delivery!
 
Processing Geospatial at Scale at LocationTech
Processing Geospatial at Scale at LocationTechProcessing Geospatial at Scale at LocationTech
Processing Geospatial at Scale at LocationTech
 
Remote sensing analysis
Remote sensing analysisRemote sensing analysis
Remote sensing analysis
 
Ahmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili BiliAhmad Mauliddin Vol Of Water In Bili Bili
Ahmad Mauliddin Vol Of Water In Bili Bili
 
Introduction to GIS
Introduction to GISIntroduction to GIS
Introduction to GIS
 
Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...
Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...
Smooth, Interactive Rendering and On-line Modification of Large-Scale, Geospa...
 
Processing Rasters from Satellites, Drones, & More
Processing Rasters from Satellites, Drones, & MoreProcessing Rasters from Satellites, Drones, & More
Processing Rasters from Satellites, Drones, & More
 

Similar to Using Deep Learning to Derive 3D Cities from Satellite Imagery

Harpster, J. - Open data on buildings with satellite imagery processing
Harpster, J. - Open data on buildings with satellite imagery processingHarpster, J. - Open data on buildings with satellite imagery processing
Harpster, J. - Open data on buildings with satellite imagery processingOECDregions
 
Bring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsBring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsDatabricks
 
Introductory Level of SLAM Seminar
Introductory Level of SLAM SeminarIntroductory Level of SLAM Seminar
Introductory Level of SLAM SeminarDong-Won Shin
 
Analysis of KinectFusion
Analysis of KinectFusionAnalysis of KinectFusion
Analysis of KinectFusionDong-Won Shin
 
Watershed Delineation Using ArcMap
Watershed Delineation Using ArcMapWatershed Delineation Using ArcMap
Watershed Delineation Using ArcMapArthur Green
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...Tulipp. Eu
 
The Matsu Project - Open Source Software for Processing Satellite Imagery Data
The Matsu Project - Open Source Software for Processing Satellite Imagery DataThe Matsu Project - Open Source Software for Processing Satellite Imagery Data
The Matsu Project - Open Source Software for Processing Satellite Imagery DataRobert Grossman
 
NetVLAD: CNN architecture for weakly supervised place recognition
NetVLAD:  CNN architecture for weakly supervised place recognitionNetVLAD:  CNN architecture for weakly supervised place recognition
NetVLAD: CNN architecture for weakly supervised place recognitionGeunhee Cho
 
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...Aritra Sarkar
 
Crowd sourcing gis for global urban area mapping
Crowd sourcing gis for global urban area mappingCrowd sourcing gis for global urban area mapping
Crowd sourcing gis for global urban area mappingHiroyuki Miyazaki
 
Transformer in Vision
Transformer in VisionTransformer in Vision
Transformer in VisionSangmin Woo
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overviewLEE HOSEONG
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong LeeMoazzem Hossain
 
The 'Rubble of the North' -a solution for modelling the irregular architectur...
The 'Rubble of the North' -a solution for modelling the irregular architectur...The 'Rubble of the North' -a solution for modelling the irregular architectur...
The 'Rubble of the North' -a solution for modelling the irregular architectur...3D ICONS Project
 
Deep Learning and Texture Mapping
Deep Learning and Texture MappingDeep Learning and Texture Mapping
Deep Learning and Texture MappingEfe Kaptan
 
Geoscience For Gis A
Geoscience For Gis AGeoscience For Gis A
Geoscience For Gis AAndrew Zolnai
 
Computer Vision Landscape : Present and Future
Computer Vision Landscape : Present and FutureComputer Vision Landscape : Present and Future
Computer Vision Landscape : Present and FutureSanghamitra Deb
 

Similar to Using Deep Learning to Derive 3D Cities from Satellite Imagery (20)

Harpster, J. - Open data on buildings with satellite imagery processing
Harpster, J. - Open data on buildings with satellite imagery processingHarpster, J. - Open data on buildings with satellite imagery processing
Harpster, J. - Open data on buildings with satellite imagery processing
 
Bring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsBring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science Workflows
 
Introductory Level of SLAM Seminar
Introductory Level of SLAM SeminarIntroductory Level of SLAM Seminar
Introductory Level of SLAM Seminar
 
Analysis of KinectFusion
Analysis of KinectFusionAnalysis of KinectFusion
Analysis of KinectFusion
 
Watershed Delineation Using ArcMap
Watershed Delineation Using ArcMapWatershed Delineation Using ArcMap
Watershed Delineation Using ArcMap
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
 
[DL輪読会]ClearGrasp
[DL輪読会]ClearGrasp[DL輪読会]ClearGrasp
[DL輪読会]ClearGrasp
 
The Matsu Project - Open Source Software for Processing Satellite Imagery Data
The Matsu Project - Open Source Software for Processing Satellite Imagery DataThe Matsu Project - Open Source Software for Processing Satellite Imagery Data
The Matsu Project - Open Source Software for Processing Satellite Imagery Data
 
NetVLAD: CNN architecture for weakly supervised place recognition
NetVLAD:  CNN architecture for weakly supervised place recognitionNetVLAD:  CNN architecture for weakly supervised place recognition
NetVLAD: CNN architecture for weakly supervised place recognition
 
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
Elevation mapping using stereo vision enabled heterogeneous multi-agent robot...
 
Crowd sourcing gis for global urban area mapping
Crowd sourcing gis for global urban area mappingCrowd sourcing gis for global urban area mapping
Crowd sourcing gis for global urban area mapping
 
Transformer in Vision
Transformer in VisionTransformer in Vision
Transformer in Vision
 
lec6a.ppt
lec6a.pptlec6a.ppt
lec6a.ppt
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overview
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee
 
The 'Rubble of the North' -a solution for modelling the irregular architectur...
The 'Rubble of the North' -a solution for modelling the irregular architectur...The 'Rubble of the North' -a solution for modelling the irregular architectur...
The 'Rubble of the North' -a solution for modelling the irregular architectur...
 
Deep Learning and Texture Mapping
Deep Learning and Texture MappingDeep Learning and Texture Mapping
Deep Learning and Texture Mapping
 
Geoscience For Gis A
Geoscience For Gis AGeoscience For Gis A
Geoscience For Gis A
 
Computer Vision Landscape : Present and Future
Computer Vision Landscape : Present and FutureComputer Vision Landscape : Present and Future
Computer Vision Landscape : Present and Future
 
Mapinfo 2014
Mapinfo 2014Mapinfo 2014
Mapinfo 2014
 

More from Astraea, Inc.

Building a Geospatial Analysis Platform - Dr. Kimberly Scott
Building a Geospatial Analysis Platform - Dr. Kimberly ScottBuilding a Geospatial Analysis Platform - Dr. Kimberly Scott
Building a Geospatial Analysis Platform - Dr. Kimberly ScottAstraea, Inc.
 
Detecting Solar Farms Using Deep Learning
Detecting Solar Farms Using Deep LearningDetecting Solar Farms Using Deep Learning
Detecting Solar Farms Using Deep LearningAstraea, Inc.
 
2018 IEEE WIE Presentation - Dr. Kimberly Scott
2018 IEEE WIE Presentation - Dr. Kimberly Scott2018 IEEE WIE Presentation - Dr. Kimberly Scott
2018 IEEE WIE Presentation - Dr. Kimberly ScottAstraea, Inc.
 
2018 Charlottesville Open Data Challenge - Team DSB
2018 Charlottesville Open Data Challenge - Team DSB2018 Charlottesville Open Data Challenge - Team DSB
2018 Charlottesville Open Data Challenge - Team DSBAstraea, Inc.
 
2018 Charlottesville Open Data Challenge - Alex Miller
2018 Charlottesville Open Data Challenge - Alex Miller2018 Charlottesville Open Data Challenge - Alex Miller
2018 Charlottesville Open Data Challenge - Alex MillerAstraea, Inc.
 
Machine Learning, FOSS, and open data to map deforestation trends in the Braz...
Machine Learning, FOSS, and open data to map deforestation trends in the Braz...Machine Learning, FOSS, and open data to map deforestation trends in the Braz...
Machine Learning, FOSS, and open data to map deforestation trends in the Braz...Astraea, Inc.
 

More from Astraea, Inc. (6)

Building a Geospatial Analysis Platform - Dr. Kimberly Scott
Building a Geospatial Analysis Platform - Dr. Kimberly ScottBuilding a Geospatial Analysis Platform - Dr. Kimberly Scott
Building a Geospatial Analysis Platform - Dr. Kimberly Scott
 
Detecting Solar Farms Using Deep Learning
Detecting Solar Farms Using Deep LearningDetecting Solar Farms Using Deep Learning
Detecting Solar Farms Using Deep Learning
 
2018 IEEE WIE Presentation - Dr. Kimberly Scott
2018 IEEE WIE Presentation - Dr. Kimberly Scott2018 IEEE WIE Presentation - Dr. Kimberly Scott
2018 IEEE WIE Presentation - Dr. Kimberly Scott
 
2018 Charlottesville Open Data Challenge - Team DSB
2018 Charlottesville Open Data Challenge - Team DSB2018 Charlottesville Open Data Challenge - Team DSB
2018 Charlottesville Open Data Challenge - Team DSB
 
2018 Charlottesville Open Data Challenge - Alex Miller
2018 Charlottesville Open Data Challenge - Alex Miller2018 Charlottesville Open Data Challenge - Alex Miller
2018 Charlottesville Open Data Challenge - Alex Miller
 
Machine Learning, FOSS, and open data to map deforestation trends in the Braz...
Machine Learning, FOSS, and open data to map deforestation trends in the Braz...Machine Learning, FOSS, and open data to map deforestation trends in the Braz...
Machine Learning, FOSS, and open data to map deforestation trends in the Braz...
 

Recently uploaded

What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfhans926745
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 

Recently uploaded (20)

What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 

Using Deep Learning to Derive 3D Cities from Satellite Imagery

  • 1. See the Earth as it could be. Eric Culbertson Data Scientist, Astraea
  • 2. • 3D buildings models have many different use cases • Solar potential estimation • Utility management • Disaster planning and simulation 2
  • 3. How are 3D Models Made? • Standard approaches: • Use LiDAR point clouds to create 3D mesh • Stitch imagery taken at multiple angles to the mesh 3
  • 4. • Constructing these 3D models can be labor intensive and expensive (both in compute power $$$) • Is there an alternative using • Free data? • Open Source tools? 4
  • 5. • Quality of 3D model is quantified by the level of detail (LOD) metric • Higher LOD = more versatile • But also more difficult to obtain 5 What do I Mean by 3D?
  • 6. • Quality of 3D model is quantified by the level of detail (LOD) metric • Higher LOD = more versatile • But also more difficult to obtain 6 What do I Mean by 3D?
  • 7. Machine Learning • Machine learning can be applied to solve difficult problems without the need of a subject matter expert • Recent advances in deep learning on images have made great strides • Machine learning tools are open source 7
  • 8. • Eventually predict labels for new data ( , ? ?) 8 ( , ) • Start by feeding many examples with the correct predictions Input imagery building footprints building height Application to Overhead Imagery
  • 9. Imagery Sources • Overhead imagery is available from many different sources in my region of interest (Las Vegas) 9 Name Source Bands Resolution (m) Coverage Revisit Cost Worldview 3 Satellite 8 0.3 m ~ Globe ~ daily $$$$$$ NAIP Aerial 4 1.0 m U.S. 3 years Free Sanborn Aerial 4 0.3 m Partial U.S. 3 years Free - $
  • 10. Imagery Sources • Overhead imagery is available from many different sources in my region of interest (Las Vegas) • Most time was spent with 2015 NAIP and 2016 Sanborn imagery 10 Name Source Bands Resolution (m) Coverage Revisit Cost Worldview 3 Satellite 8 0.3 m ~ Globe ~ daily $$$$$$ NAIP Aerial 4 1.0 m U.S. 3 years Free Sanborn Aerial 4 0.3 m Partial U.S. 3 years Free - $
  • 12. Ground Truth • Building footprint polygons were provided by the SpaceNet Challenge • Rasterized with rasterio, shapely, and numpy python modules • Pixel height truth was derived from 2012 LiDAR data found on USGS • Quality level is not ideal (pulse density ~ .3 pulses / m2) 12 Raw Lidar point cloud tiles Filter outliers Merge tiles Height above ground Reproject Rasterize Pixel heights Las2las PDAL CloudCompare
  • 13. Neuron / Perceptron 13 11 11 8 2 𝑤𝑖 ∗ 𝑥𝑖 Weighted sum Cat Prediction Body length Tail length Weight Number of ears Activation Dog
  • 14. Neural Network 14 10 11 8 2 Sum + activation Cat Prediction Body length Tail length Weight Number of ears 1.0 8 Body length Tail length Weight • Nesting layers of neurons allows the network to learn more complicated features Dog
  • 15. Convolutional Neural Network • CNNs are a way to extract important features from an image to make a prediction 15LearnedFeatures Sum + activation Prediction Cat Dog
  • 16. CNN Image Segmentation 16 • CNNs also can be used to make predictions per-pixel by determining important features in regions around that pixel U-net architecture
  • 17. Application to Overhead Imagery 17 Predict footprints Predict pixel height • Similar features are used to determine the building footprint and height • Combining the learning process shares knowledge gained from learning each task • This saves time and manual effort Input imagery Shared weights Combine To make 2.5D model
  • 18. • Keras was used to implement the U-net architecture • High level wrapper of either Tensorflow, Theano or CNTK • Allows for fast experimentation • Simple to use, but flexible 18 FOSS for Deep Learning
  • 19. • NAIP shows some promise in getting building height • Roof shape seems beyond its capability 19 NAIP imagery LiDAR Height Predicted Height
  • 20. Challenges 20 NAIP imagery Lidar Height This is a ditch, not a raised area
  • 21. Challenges 21 • NAIP and Sanborn imagery do not line up well with ground truth polygons • Offset is not consistent
  • 22. NAIP Results • Accuracy of only 35% • Performs well on short structures • Biased to predict 2 story buildings 22 Predicted Num Stories TrueNumStories
  • 23. Sanborn Results • Accuracy improves to 56% • Still struggles on residential sized buildings 23 Predicted Num Stories TrueNumStories
  • 27. Conclusions • Promising • On the horizon • Needs better height data • Needs high res imagery 27
  • 28. Acknowledgements • SpaceNet Challenge • Accurate ground truth footprints were quite valuable • Kohei Ozaki • His solution to the SpaceNet challenge introduced me to image segmentation 28

Editor's Notes

  1. Focus on use cases for 3d models Look more at that paper Expand on solar Population estimation, noise porpogation, energy consumption
  2. Learn more about photogrammetry Potentially split into two slides Another slide to expand on why they are expensive and difficult and time consuming Not scalable
  3. Machine learning Open source software Open data Cheap, fast, easy, scalable
  4. Add 3d image